Skip to content

reference impl with llama.cpp compiled to distributed inference across machines, with real end to end demo

active 2026-03-242026-04-13 (UTC)

Partial coverage11,302 / 12,123 hourly files (93%) · 2 absent upstream · 818 failed, retryable2025-03-232026-08-10 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
1.3K
Pushes
472
Pull requests
74
Issues
25
Stars
128
Forks
8

Activity over time

Daily event counts in the loaded window

Line chart, 21 days from 2026-03-24 to 2026-04-13. Pushes: 472 total, peak 61 in a day. Pull requests: 74 total, peak 8 in a day. Issues: 25 total, peak 6 in a day. Comments: 354 total, peak 44 in a day. Stars: 128 total, peak 40 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
i3864453003469
Copilot387427247
michaelneale128801816
ndizazzo104501317
Bortlesboat3011
jmecom2001
sheikhlimon2001
IvGolovach2011
sanoakr1000
abadiegie1001

Recent activity

Latest issues, pull requests and releases

  • Issue comment#261i3862026-04-13 00:57
    Fix Hugging Face job pricing decode for hardware flavors
  • Pull request#258michaelneale2026-04-12 23:31
  • Pull request#257michaelneale2026-04-12 22:20
  • Issue#256michaelneale2026-04-12 22:11
    feature: make mesh-llm app load aware to stop/start models depending on local usage
  • Pull request#255ndizazzo2026-04-12 22:03
  • Pull request#253i3862026-04-12 21:24
  • Pull request#252i3862026-04-12 21:09
  • Pull request#252i3862026-04-12 20:27
  • Issue#115ndizazzo2026-04-12 20:18
    feature: dockerized setup for K3S / container environments
  • Issue#174i3862026-04-12 10:10
    Scope child-process cleanup to the owning mesh-llm instance and surface mixed-version state
  • Pull request#217ndizazzo2026-04-12 10:10
  • Pull request#248ndizazzo2026-04-12 09:01
  • Issue comment#217Copilot2026-04-12 07:33
    runtime: introduce scoped instance runtime with safe process lifecycle management
  • Issue comment#232i3862026-04-12 07:07
    split serving: recover dense models on surviving workers
  • Issue comment#248i3862026-04-12 06:58
    feat(hardware): add hardware information enrichment
  • Issue comment#233Copilot2026-04-12 03:30
    feature: add embedded SDK support
  • Pull request#251i3862026-04-11 19:37
  • Pull request#250i3862026-04-11 04:06
  • Pull request#244i3862026-04-11 00:01
  • Issue comment#244Copilot2026-04-10 23:06
    Add MoE ranking publishing workflow and ship llama-moe-analyze in release bundles
  • Issue comment#244i3862026-04-10 23:02
    Add MoE ranking publishing workflow and ship llama-moe-analyze in release bundles
  • Pull request#242michaelneale2026-04-10 22:17
  • Issue#136ndizazzo2026-04-10 17:19
    Add hardware runtime status enrichment without changing model metadata sources
  • Issue comment#240ndizazzo2026-04-10 16:36
    revise mesh publication rules
  • Pull request#239ndizazzo2026-04-10 15:50

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 128 stars here means stars gained during the window, not the repo's star count.